PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Heterogeneous Information Fusion: A Novel Fusion Paradigm for Biometric Systems
Norman Poh, A Merati and Josef Kittler
In: Int'l. Joint Conf. On Biometrics (IJCB), Washington DC, USA(2011).

Abstract

One of the most promising ways to improve biometric person recognition is indisputably via information fusion, that is, to combine different sources of information. This paper proposes a novel fusion paradigm that combines heterogeneous sources of information such as user-specific, cohort and quality information. Two formulations of this problem are proposed, differing in the assumption on the independence of the information sources. Unlike the more common multimodal/multi-algorithmic fusion, the novel paradigm has to deal with information that is not necessarily discriminative but still it is relevant. The methodology can be applied to any biometric system. Furthermore, extensive experiments based on 30 face and fingerprint experiments indicate that the performance gain with respect to the baseline system is about 30%. In contrast, solving this problem using conventional fusion paradigm leads to degraded results.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Multimodal Integration
ID Code:8880
Deposited By:Norman Poh
Deposited On:21 February 2012